PRELIMINARY EMPIRICAL RESULTS SUGGESTING THE MAPPING OF DYNAMIC IN-SITU PROCESS SIGNALS TO REAL-TIME WAFER ATTRIBUTES IN A PLASMA ETCH PROCESS

In many chemical engineering processes the input control parameters an d the product output quality are monitored dynamically in real-time. A lmost all the processing steps associated with semiconductor manufactu ring are chemical processes in which the surface of crystals or thin f ilms are being chemically modified. In situ monitoring of the wafer at tributes in real-time is essentially nonexistent in modern semiconduct or manufacturing. For plasma etching processes several new diagnostic techniques (e.g., full-wafer imaging interferometry and ellipsometry) provide improved endpoint observation and some provide metrics for the state of the wafer at a given time. However, the methods that do prov ide metrics are usually quite expensive for a manufacturing environmen t. We propose a method whereby simple and economic endpoint methods ca n indicate in real-time the state of the wafer. Our method consists of finding the algorithm to map in situ wafer-state signatures (e.g., in terferometry, ellipsometry) to wafer attributes and then mapping the p rocess signatures (e.g., reflected rf power, pressure, flow rate, OES) to wafer-state signatures. From these we then have an abstract mappin g from the process signatures to the wafer attributes in real-time. In this article we suggest that a learning machine can perform the mappi ng between process signatures, as a function of time and wafer state s ignatures, as a function of time. (C) 1998 American Vacuum Society.